{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XOSOEONSJYMX3MT3KK3NCLWNP3","short_pith_number":"pith:XOSOEONS","schema_version":"1.0","canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","source":{"kind":"arxiv","id":"1805.07470","version":1},"attestation_state":"computed","paper":{"title":"Solving the Rubik's Cube Without Human Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Shmakov, Forest Agostinelli, Pierre Baldi, Stephen McAleer","submitted_at":"2018-05-18T23:07:31Z","abstract_excerpt":"A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms combined with self-play have achieved superhuman proficiency in Go, Chess, and Shogi without human data or domain knowledge. In these environments, a reward is always received at the end of the game, however, for many combinatorial optimization environments, rewards are sparse and episodes are not guaranteed to terminate. We introduce Autodidactic Iteration: a novel reinforcement learning algorithm that is able to t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.07470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-18T23:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"63e2506c805daa32707aab16f64f8a521a2971142d854db12cf9b0c011136e50","abstract_canon_sha256":"6f61c2b50e4d7b39adabc5d981416db928940fc83c226944339c1982644c64d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:33.497187Z","signature_b64":"x8ndrosGChaaQCG3Qk5sqrZcRq4JJmEuEyfADwzTRWfgPOeXFMqpl4fFY1aLIk5Wem7dB91A13UgS5cLqab8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba4e239b24e197db27b52b6d12ecd7ede616a3d67e684f45024aa8507d131b6","last_reissued_at":"2026-05-18T00:15:33.496573Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:33.496573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving the Rubik's Cube Without Human Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Shmakov, Forest Agostinelli, Pierre Baldi, Stephen McAleer","submitted_at":"2018-05-18T23:07:31Z","abstract_excerpt":"A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms combined with self-play have achieved superhuman proficiency in Go, Chess, and Shogi without human data or domain knowledge. In these environments, a reward is always received at the end of the game, however, for many combinatorial optimization environments, rewards are sparse and episodes are not guaranteed to terminate. We introduce Autodidactic Iteration: a novel reinforcement learning algorithm that is able to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07470","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.07470","created_at":"2026-05-18T00:15:33.496654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07470v1","created_at":"2026-05-18T00:15:33.496654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07470","created_at":"2026-05-18T00:15:33.496654+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOSOEONSJYMX","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOSOEONSJYMX3MT3","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOSOEONS","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3","json":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3.json","graph_json":"https://pith.science/api/pith-number/XOSOEONSJYMX3MT3KK3NCLWNP3/graph.json","events_json":"https://pith.science/api/pith-number/XOSOEONSJYMX3MT3KK3NCLWNP3/events.json","paper":"https://pith.science/paper/1805.07470"},"agent_actions":{"view_html":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3","download_json":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3.json","view_paper":"https://pith.science/paper/1805.07470","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07470&json=true","fetch_graph":"https://pith.science/api/pith-number/XOSOEONSJYMX3MT3KK3NCLWNP3/graph.json","fetch_events":"https://pith.science/api/pith-number/XOSOEONSJYMX3MT3KK3NCLWNP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/action/storage_attestation","attest_author":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/action/author_attestation","sign_citation":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/action/citation_signature","submit_replication":"https://pith.science/pith/XOSOEONSJYMX3MT3KK3NCLWNP3/action/replication_record"}},"created_at":"2026-05-18T00:15:33.496654+00:00","updated_at":"2026-05-18T00:15:33.496654+00:00"}